Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "the" and its linguistic variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    legal citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.58
     <<<<<<<<<<<<<<
    -0.57
    richTextPanel
    -0.56
    клопе
    -0.54
     ujednoznacz
    -0.54
    parsedMessage
    -0.54
    -0.52
    jsonwebtoken
    -0.52
     typelib
    -0.51
    WithIOException
    -0.50
    POSITIVE LOGITS
    LEMMA
    0.39
    Redo
    0.39
     карьера
    0.36
    Véase
    0.35
    枉
    0.35
     Procedures
    0.35
    Procedure
    0.34
     importance
    0.34
     fix
    0.34
    Pageable
    0.34
    Act Density 0.015%

    No Known Activations